论文信息 - Comparative evaluation of recommender system quality

Comparative evaluation of recommender system quality

Several researchers suggest that the Recommendation Systems (RSs) that are the "best" according to statistical metrics might not be the most satisfactory for the user. We explored this issue through an empirical study that involved 210 users and considered 7 RSs using different recommender algorithms on the same dataset. We measured user's perceived quality of each RS, and compared these results against measures of statistical quality of the considered algorithms as they have been assessed by past studies in the field, highlighting some interesting results.

[1] Rong Hu,et al. Acceptance issues of personality-based recommender systems , 2009, RecSys '09.

[2] Pearl Pu,et al. User Technology Adoption Issues in Recommender Systems , 2007 .

[3] Sean M. McNee,et al. Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.

[4] Kirsten Swearingen,et al. Beyond Algorithms: An HCI Perspective on Recommender Systems , 2001 .

[5] Li Chen,et al. Evaluating product search and recommender systems for E-commerce environments , 2008, Electron. Commer. Res..

[6] Li Chen,et al. A cross-cultural user evaluation of product recommender interfaces , 2008, RecSys '08.

[7] Pearl Pu,et al. Critiquing recommenders for public taste products , 2009, RecSys '09.

[8] John Riedl,et al. An algorithmic framework for performing collaborative filtering , 1999, SIGIR '99.

[9] Roberto Turrin,et al. Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

[10] Li Chen,et al. A user-centric evaluation framework for recommender systems , 2011, RecSys '11.

[11] Jonathan L. Herlocker,et al. Evaluating collaborative filtering recommender systems , 2004, TOIS.